rcu: Provide optional RCU-reader exit delay for strict GPs

The goal of this series is to increase the probability of tools like
KASAN detecting that an RCU-protected pointer was used outside of its
RCU read-side critical section.  Thus far, the approach has been to make
grace periods and callback processing happen faster.  Another approach
is to delay the pointer leaker.  This commit therefore allows a delay
to be applied to exit from RCU read-side critical sections.

This slowdown is specified by a new rcutree.rcu_unlock_delay kernel boot
parameter that specifies this delay in microseconds, defaulting to zero.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 60e2c6e..c532c70 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4128,6 +4128,15 @@
 			This wake_up() will be accompanied by a
 			WARN_ONCE() splat and an ftrace_dump().
 
+	rcutree.rcu_unlock_delay= [KNL]
+			In CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels,
+			this specifies an rcu_read_unlock()-time delay
+			in microseconds.  This defaults to zero.
+			Larger delays increase the probability of
+			catching RCU pointer leaks, that is, buggy use
+			of RCU-protected pointers after the relevant
+			rcu_read_unlock() has completed.
+
 	rcutree.sysrq_rcu= [KNL]
 			Commandeer a sysrq key to dump out Tree RCU's
 			rcu_node tree with an eye towards determining
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1761ff4..2f1de27 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -430,6 +430,12 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
 	return !list_empty(&rnp->blkd_tasks);
 }
 
+// Add delay to rcu_read_unlock() for strict grace periods.
+#ifdef CONFIG_RCU_STRICT_GRACE_PERIOD
+static int rcu_unlock_delay;
+module_param(rcu_unlock_delay, int, 0444);
+#endif
+
 /*
  * Report deferred quiescent states.  The deferral time can
  * be quite short, for example, in the case of the call from
@@ -460,10 +466,12 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	}
 	t->rcu_read_unlock_special.s = 0;
 	if (special.b.need_qs) {
-		if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
+		if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) {
 			rcu_report_qs_rdp(rdp->cpu, rdp);
-		else
+			udelay(rcu_unlock_delay);
+		} else {
 			rcu_qs();
+		}
 	}
 
 	/*